已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整的填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-Ray Image

特征(语言学) 编码(集合论) 计算机科学 卷积(计算机科学) 人工智能 特征提取 模式识别(心理学) 图像(数学) 焊接 卷积神经网络 人工神经网络 计算机视觉 工程类 机械工程 哲学 集合(抽象数据类型) 程序设计语言 语言学
作者
Moyun Liu,Youping Chen,Jingming Xie,Lei He,Yang Zhang
出处
期刊:IEEE Sensors Journal [Institute of Electrical and Electronics Engineers]
卷期号:23 (7): 7430-7439 被引量:38
标识
DOI:10.1109/jsen.2023.3247006
摘要

X-ray image plays an important role in manufacturing industry for quality assurance, because it can reflect the internal condition of weld region. However, the shape and scale of different defect types vary greatly, which makes it challenging for model to detect weld defects. In this article, we propose a weld defect detection method based on convolution neural network (CNN), namely, lighter and faster YOLO (LF-YOLO). In particular, a reinforced multiscale feature (RMF) module is designed to implement both parameter-based and parameter-free multiscale information extracting operations. RMF enables the extracted feature map to represent more plentiful information, which is achieved by a superior hierarchical fusion structure. To improve the performance of detection network, we propose an efficient feature extraction (EFE) module. EFE processes input data with extremely low consumption and improves the practicability of whole network in actual industry. Experimental results show that our weld defect detection network achieves satisfactory balance between performance and consumption and reaches 92.9 mean average precision (mAP50) with 61.5 frames/s. To further prove the ability of our method, we test it on the public dataset MS COCO, and the results show that our LF-YOLO has an outstanding versatility detection performance. The code is available at https://github.com/lmomoy/LF-YOLO .
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
xiaodu20230228完成签到 ,获得积分10
刚刚
刚刚
烦烦发布了新的文献求助10
刚刚
斯文败类应助nenoaowu采纳,获得10
1秒前
万能图书馆应助nenoaowu采纳,获得10
1秒前
Owen应助nenoaowu采纳,获得10
1秒前
科目三应助nenoaowu采纳,获得10
1秒前
缓慢的谷秋应助nenoaowu采纳,获得10
1秒前
今后应助nenoaowu采纳,获得10
1秒前
Ava应助nenoaowu采纳,获得30
1秒前
Lucas应助nenoaowu采纳,获得10
1秒前
李健的小迷弟应助nenoaowu采纳,获得50
1秒前
上官若男应助nenoaowu采纳,获得10
1秒前
刘洲阳发布了新的文献求助30
1秒前
2秒前
2秒前
完美的芙蓉完成签到 ,获得积分10
3秒前
杨森omg应助今天不熬夜采纳,获得10
4秒前
xaoi发布了新的文献求助10
5秒前
6秒前
daifei应助兔子小乖乖采纳,获得10
8秒前
思明完成签到 ,获得积分10
8秒前
森林里的星星完成签到,获得积分10
9秒前
科研通AI2S应助奥利奥利奥采纳,获得10
9秒前
14秒前
14秒前
滑板发布了新的文献求助10
14秒前
15秒前
舒伯特完成签到 ,获得积分10
16秒前
lan发布了新的文献求助10
19秒前
kuan完成签到,获得积分20
19秒前
英姑应助xaoi采纳,获得20
19秒前
一颗橙子发布了新的文献求助30
21秒前
爆米花应助科研通管家采纳,获得10
22秒前
传奇3应助科研通管家采纳,获得10
22秒前
小蘑菇应助科研通管家采纳,获得10
22秒前
sutharsons应助科研通管家采纳,获得30
22秒前
sutharsons应助科研通管家采纳,获得30
22秒前
sutharsons应助科研通管家采纳,获得30
22秒前
sutharsons应助科研通管家采纳,获得30
22秒前
高分求助中
Spray / Wall-interaction Modelling by Dimensionless Data Analysis 2000
Aspects of Babylonian celestial divination: the lunar eclipse tablets of Enūma Anu Enlil 500
Mathematics and Finite Element Discretizations of Incompressible Navier—Stokes Flows 500
India's foreign trade policy and its performance in the world economy 450
Dictionary of socialism 350
Mixed-anion Compounds 300
Geochemistry, 2nd Edition 地球化学经典教科书第二版 300
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3196434
求助须知:如何正确求助?哪些是违规求助? 2845181
关于积分的说明 8053289
捐赠科研通 2509844
什么是DOI,文献DOI怎么找? 1342009
科研通“疑难数据库(出版商)”最低求助积分说明 639304
邀请新用户注册赠送积分活动 608565